Solidity Security Audit LoRA

Fine-tuned LoRA on 2000 smart contract security findings from Code4rena.

Training

  • Base: Mistral-7B-Instruct-v0.2
  • Dataset: 9,359 findings (HIGH/MEDIUM severity)
  • Epochs: 2
  • Final loss: 0.888
  • Token accuracy: 79%

Usage

Load with PEFT on top of Mistral-7B-Instruct-v0.2.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for xanoutas/solidity-security-lora

Adapter
(1244)
this model